Search Results for author: HuaWei Shen

Found 71 papers, 40 papers with code

Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases

no code implementations COLING 2022 Kun Zhang, Yunqi Qiu, Yuanzhuo Wang, Long Bai, Wei Li, Xuhui Jiang, HuaWei Shen, Xueqi Cheng

Complex question generation over knowledge bases (KB) aims to generate natural language questions involving multiple KB relations or functional constraints.

Contrastive Learning Meta-Learning +2

Unlocking the Power of Large Language Models for Entity Alignment

no code implementations23 Feb 2024 Xuhui Jiang, Yinghan Shen, Zhichao Shi, Chengjin Xu, Wei Li, Zixuan Li, Jian Guo, HuaWei Shen, Yuanzhuo Wang

To address the constraints of limited input KG data, ChatEA introduces a KG-code translation module that translates KG structures into a format understandable by LLMs, thereby allowing LLMs to utilize their extensive background knowledge to improve EA accuracy.

Code Translation Entity Alignment +2

Qsnail: A Questionnaire Dataset for Sequential Question Generation

1 code implementation22 Feb 2024 Yan Lei, Liang Pang, Yuanzhuo Wang, HuaWei Shen, Xueqi Cheng

Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure.

Question Generation Question-Generation +1

Event-aware Video Corpus Moment Retrieval

no code implementations21 Feb 2024 Danyang Hou, Liang Pang, HuaWei Shen, Xueqi Cheng

Video Corpus Moment Retrieval (VCMR) is a practical video retrieval task focused on identifying a specific moment within a vast corpus of untrimmed videos using the natural language query.

Contrastive Learning Moment Retrieval +4

Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement

no code implementations21 Feb 2024 Danyang Hou, Liang Pang, HuaWei Shen, Xueqi Cheng

The relevance between the video and query is partial, mainly evident in two aspects: (1) Scope: The untrimmed video contains information-rich frames, and not all are relevant to the query.

Moment Retrieval Retrieval +2

Stable Knowledge Editing in Large Language Models

no code implementations20 Feb 2024 Zihao Wei, Liang Pang, Hanxing Ding, Jingcheng Deng, HuaWei Shen, Xueqi Cheng

The premise of localization results in an incomplete knowledge editing, whereas an isolated assumption may impair both other knowledge and general abilities.

knowledge editing

Retrieve Only When It Needs: Adaptive Retrieval Augmentation for Hallucination Mitigation in Large Language Models

no code implementations16 Feb 2024 Hanxing Ding, Liang Pang, Zihao Wei, HuaWei Shen, Xueqi Cheng

A careful and balanced integration of the parametric knowledge within LLMs with external information is crucial to alleviate hallucinations.

Hallucination Retrieval

Unlink to Unlearn: Simplifying Edge Unlearning in GNNs

no code implementations16 Feb 2024 Jiajun Tan, Fei Sun, Ruichen Qiu, Du Su, HuaWei Shen

To address this issue, we have identified the loss functions of GNNDelete as the primary source of the over-forgetting phenomenon.

Link Prediction

LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks

no code implementations31 Jan 2024 Kaike Zhang, Qi Cao, Yunfan Wu, Fei Sun, HuaWei Shen, Xueqi Cheng

Traditional defense strategies predominantly depend on predefined assumptions or rules extracted from specific known attacks, limiting their generalizability to unknown attack types.

Language Modelling Large Language Model +2

TEA: Test-time Energy Adaptation

1 code implementation24 Nov 2023 Yige Yuan, Bingbing Xu, Liang Hou, Fei Sun, HuaWei Shen, Xueqi Cheng

To address this, we propose a novel energy-based perspective, enhancing the model's perception of target data distributions without requiring access to training data or processes.


AI-Generated Images Introduce Invisible Relevance Bias to Text-Image Retrieval

no code implementations23 Nov 2023 Shicheng Xu, Danyang Hou, Liang Pang, Jingcheng Deng, Jun Xu, HuaWei Shen, Xueqi Cheng

Furthermore, our subsequent exploration reveals that the inclusion of AI-generated images in the training data of the retrieval models exacerbates the invisible relevance bias.

Cross-Modal Retrieval Image Retrieval +2

Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue

no code implementations13 Nov 2023 Junkai Zhou, Liang Pang, HuaWei Shen, Xueqi Cheng

The emergence of large language models (LLMs) further improves the capabilities of open-domain dialogue systems and can generate fluent, coherent, and diverse responses.

Dialogue Generation In-Context Learning +2

Plot Retrieval as an Assessment of Abstract Semantic Association

no code implementations3 Nov 2023 Shicheng Xu, Liang Pang, Jiangnan Li, Mo Yu, Fandong Meng, HuaWei Shen, Xueqi Cheng, Jie zhou

Readers usually only give an abstract and vague description as the query based on their own understanding, summaries, or speculations of the plot, which requires the retrieval model to have a strong ability to estimate the abstract semantic associations between the query and candidate plots.

Information Retrieval Retrieval

DyTSCL: Dynamic graph representation via tempo-structural contrastive learning

1 code implementation journal 2023 Jianian Li, Peng Bao, Rong Yan, HuaWei Shen

In this paper, we propose a novel Dynamic graph representation framework via Tempo-Structural Contrastive Learning, DyTSCL, which trains the model by identifying three different subgraphs as a task, named Tempo-Structural subgraph, Non-Temporal subgraph and Non-Structural subgraph.

Contrastive Learning Graph Learning +1

RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling

1 code implementation16 Oct 2023 Jingcheng Deng, Liang Pang, HuaWei Shen, Xueqi Cheng

It encodes the text corpus into a latent space, capturing current and future information from both source and target text.

Hallucination Language Modelling +2

Causality and Independence Enhancement for Biased Node Classification

1 code implementation14 Oct 2023 Guoxin Chen, Yongqing Wang, Fangda Guo, Qinglang Guo, Jiangli Shao, HuaWei Shen, Xueqi Cheng

Most existing methods that address out-of-distribution (OOD) generalization for node classification on graphs primarily focus on a specific type of data biases, such as label selection bias or structural bias.

Classification Node Classification +1

Robust Recommender System: A Survey and Future Directions

no code implementations5 Sep 2023 Kaike Zhang, Qi Cao, Fei Sun, Yunfan Wu, Shuchang Tao, HuaWei Shen, Xueqi Cheng

With the rapid growth of information, recommender systems have become integral for providing personalized suggestions and overcoming information overload.

Fairness Recommendation Systems +1

Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer

no code implementations18 Aug 2023 Wendong Bi, Xueqi Cheng, Bingbing Xu, Xiaoqian Sun, Li Xu, HuaWei Shen

Transfer learning has been a feasible way to transfer knowledge from high-quality external data of source domains to limited data of target domains, which follows a domain-level knowledge transfer to learn a shared posterior distribution.

Retrieval Transfer Learning

OpenGDA: Graph Domain Adaptation Benchmark for Cross-network Learning

1 code implementation21 Jul 2023 Boshen Shi, Yongqing Wang, Fangda Guo, Jiangli Shao, HuaWei Shen, Xueqi Cheng

Overall, OpenGDA provides a user-friendly, scalable and reproducible benchmark for evaluating graph domain adaptation models.

Domain Adaptation Node Classification

PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion

1 code implementation25 May 2023 Yige Yuan, Bingbing Xu, Bo Lin, Liang Hou, Fei Sun, HuaWei Shen, Xueqi Cheng

The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones.

Data Augmentation

IDEA: Invariant Causal Defense for Graph Adversarial Robustness

no code implementations25 May 2023 Shuchang Tao, Qi Cao, HuaWei Shen, Yunfan Wu, Bingbing Xu, Xueqi Cheng

Through modeling and analyzing the causal relationships in graph adversarial attacks, we design two invariance objectives to learn the causal features.

Adversarial Robustness

MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space

1 code implementation22 May 2023 Hanxing Ding, Liang Pang, Zihao Wei, HuaWei Shen, Xueqi Cheng, Tat-Seng Chua

Multi-aspect controllable text generation aims to generate fluent sentences that possess multiple desired attributes simultaneously.

Attribute Text Generation

Popularity Debiasing from Exposure to Interaction in Collaborative Filtering

1 code implementation9 May 2023 YuanHao Liu, Qi Cao, HuaWei Shen, Yunfan Wu, Shuchang Tao, Xueqi Cheng

In this paper, we propose a new criterion for popularity debiasing, i. e., in an unbiased recommender system, both popular and unpopular items should receive Interactions Proportional to the number of users who Like it, namely IPL criterion.

Collaborative Filtering Recommendation Systems

Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks

1 code implementation28 Apr 2023 Shicheng Xu, Liang Pang, HuaWei Shen, Xueqi Cheng, Tat-Seng Chua

This paper proposes a novel framework named \textbf{Search-in-the-Chain} (SearChain) for the interaction between LLM and IR to solve the challenges.

Fact Checking Information Retrieval +7

Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets

1 code implementation7 Apr 2023 Xuhui Jiang, Chengjin Xu, Yinghan Shen, Yuanzhuo Wang, Fenglong Su, Fei Sun, Zixuan Li, Zhichao Shi, Jian Guo, HuaWei Shen

Firstly, we address the oversimplified heterogeneity settings of current datasets and propose two new HHKG datasets that closely mimic practical EA scenarios.

Entity Alignment Knowledge Graphs +1

Graph Adversarial Immunization for Certifiable Robustness

1 code implementation16 Feb 2023 Shuchang Tao, HuaWei Shen, Qi Cao, Yunfan Wu, Liang Hou, Xueqi Cheng

In this paper, we propose and formulate graph adversarial immunization, i. e., vaccinating part of graph structure to improve certifiable robustness of graph against any admissible adversarial attack.

Adversarial Attack Combinatorial Optimization

Adversarial Learning Data Augmentation for Graph Contrastive Learning in Recommendation

1 code implementation5 Feb 2023 JunJie Huang, Qi Cao, Ruobing Xie, Shaoliang Zhang, Feng Xia, HuaWei Shen, Xueqi Cheng

To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance.

Contrastive Learning Data Augmentation

Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network

1 code implementation2 Feb 2023 Wendong Bi, Bingbing Xu, Xiaoqian Sun, Li Xu, HuaWei Shen, Xueqi Cheng

To combat the above challenges, we propose Knowledge Transferable Graph Neural Network (KT-GNN), which models distribution shifts during message passing and representation learning by transferring knowledge from vocal nodes to silent nodes.

Representation Learning

Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks

1 code implementation31 Jan 2023 Wendong Bi, Bingbing Xu, Xiaoqian Sun, Zidong Wang, HuaWei Shen, Xueqi Cheng

However, most nodes in the tribe-style graph lack attributes, making it difficult to directly adopt existing graph learning methods (e. g., Graph Neural Networks(GNNs)).

Contrastive Learning Graph Learning

Multi-video Moment Ranking with Multimodal Clue

no code implementations29 Jan 2023 Danyang Hou, Liang Pang, Yanyan Lan, HuaWei Shen, Xueqi Cheng

In this paper, we focus on improving two problems of two-stage method: (1) Moment prediction bias: The predicted moments for most queries come from the top retrieved videos, ignoring the possibility that the target moment is in the bottom retrieved videos, which is caused by the inconsistency of Shared Normalization during training and inference.

Moment Retrieval Retrieval +1

Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding

no code implementations10 Jan 2023 Yunchang Zhu, Liang Pang, Kangxi Wu, Yanyan Lan, HuaWei Shen, Xueqi Cheng

Comparative loss is essentially a ranking loss on top of the task-specific losses of the full and ablated models, with the expectation that the task-specific loss of the full model is minimal.

Natural Language Understanding Network Pruning

NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework

1 code implementation1 Dec 2022 Shicheng Xu, Liang Pang, HuaWei Shen, Xueqi Cheng

Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they share the same schema to estimate the relationship between texts.

Information Retrieval Open-Domain Question Answering +1

Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective

no code implementations20 Nov 2022 Yige Yuan, Bingbing Xu, HuaWei Shen, Qi Cao, Keting Cen, Wen Zheng, Xueqi Cheng

Guided by the bound, we design a GCL framework named InfoAdv with enhanced generalization ability, which jointly optimizes the generalization metric and InfoMax to strike the right balance between pretext task fitting and the generalization ability on downstream tasks.

Contrastive Learning Data Augmentation +1

Hierarchical Estimation for Effective and Efficient Sampling Graph Neural Network

no code implementations16 Nov 2022 Yang Li, Bingbing Xu, Qi Cao, Yige Yuan, HuaWei Shen

On account that previous studies either lacks variance analysis or only focus on a particular sampling paradigm, we firstly propose an unified node sampling variance analysis framework and analyze the core challenge "circular dependency" for deriving the minimum variance sampler, i. e., sampling probability depends on node embeddings while node embeddings can not be calculated until sampling is finished.

Time Series Time Series Analysis

Adversarial Camouflage for Node Injection Attack on Graphs

1 code implementation3 Aug 2022 Shuchang Tao, Qi Cao, HuaWei Shen, Yunfan Wu, Liang Hou, Fei Sun, Xueqi Cheng

In this paper, we first propose and define camouflage as distribution similarity between ego networks of injected nodes and normal nodes.

Learning node embeddings via summary graphs: a brief theoretical analysis

no code implementations4 Jul 2022 Houquan Zhou, Shenghua Liu, Danai Koutra, HuaWei Shen, Xueqi Cheng

Recent works try to improve scalability via graph summarization -- i. e., they learn embeddings on a smaller summary graph, and then restore the node embeddings of the original graph.

Graph Mining Graph Representation Learning

Few-Shot Stance Detection via Target-Aware Prompt Distillation

no code implementations27 Jun 2022 Yan Jiang, Jinhua Gao, HuaWei Shen, Xueqi Cheng

The main challenge of this task comes two-fold: few-shot learning resulting from the varying targets and the lack of contextual information of the targets.

Few-Shot Learning Stance Detection

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

1 code implementation25 Apr 2022 Yunchang Zhu, Liang Pang, Yanyan Lan, HuaWei Shen, Xueqi Cheng

Ideally, if a PRF model can distinguish between irrelevant and relevant information in the feedback, the more feedback documents there are, the better the revised query will be.


Transductive Learning for Unsupervised Text Style Transfer

1 code implementation EMNLP 2021 Fei Xiao, Liang Pang, Yanyan Lan, Yan Wang, HuaWei Shen, Xueqi Cheng

The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.

Retrieval Style Transfer +3

Single Node Injection Attack against Graph Neural Networks

1 code implementation30 Aug 2021 Shuchang Tao, Qi Cao, HuaWei Shen, JunJie Huang, Yunfan Wu, Xueqi Cheng

In this paper, we focus on an extremely limited scenario of single node injection evasion attack, i. e., the attacker is only allowed to inject one single node during the test phase to hurt GNN's performance.

Signed Bipartite Graph Neural Networks

1 code implementation22 Aug 2021 JunJie Huang, HuaWei Shen, Qi Cao, Shuchang Tao, Xueqi Cheng

Signed bipartite networks are different from classical signed networks, which contain two different node sets and signed links between two node sets.

Link Sign Prediction Network Embedding

Conditional GANs with Auxiliary Discriminative Classifier

2 code implementations21 Jul 2021 Liang Hou, Qi Cao, HuaWei Shen, Siyuan Pan, Xiaoshuang Li, Xueqi Cheng

Specifically, the proposed auxiliary discriminative classifier becomes generator-aware by recognizing the class-labels of the real data and the generated data discriminatively.

Conditional Image Generation Generative Adversarial Network

INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering

1 code implementation12 Jul 2021 Yunfan Wu, Qi Cao, HuaWei Shen, Shuchang Tao, Xueqi Cheng

INMO generates the inductive embeddings for users (items) by characterizing their interactions with some template items (template users), instead of employing an embedding lookup table.

Collaborative Filtering Recommendation Systems

Self-Supervised GANs with Label Augmentation

2 code implementations NeurIPS 2021 Liang Hou, HuaWei Shen, Qi Cao, Xueqi Cheng

Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment.

Data Augmentation Image Generation +2

Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning

1 code implementation21 Apr 2021 Zixuan Li, Xiaolong Jin, Wei Li, Saiping Guan, Jiafeng Guo, HuaWei Shen, Yuanzhuo Wang, Xueqi Cheng

To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently.

Representation Learning

Locate Who You Are: Matching Geo-location to Text for User Identity Linkage

no code implementations19 Apr 2021 Jiangli Shao, Yongqing Wang, Hao Gao, HuaWei Shen, Yangyang Li, Xueqi Cheng

However, encouraged by online services, users would also post asymmetric information across networks, such as geo-locations and texts.

Anchor link prediction Marketing

GCN-ALP: Addressing Matching Collisions in Anchor Link Prediction

no code implementations19 Mar 2021 Hao Gao, Yongqing Wang, Shanshan Lyu, HuaWei Shen, Xueqi Cheng

However, the low quality of observed user data confuses the judgment on anchor links, resulting in the matching collision problem in practice.

Anchor link prediction

Modelling Universal Order Book Dynamics in Bitcoin Market

no code implementations15 Jan 2021 Fabin Shi, Nathan Aden, Shengda Huang, Neil Johnson, Xiaoqian Sun, Jinhua Gao, Li Xu, HuaWei Shen, Xueqi Cheng, Chaoming Song

Understanding the emergence of universal features such as the stylized facts in markets is a long-standing challenge that has drawn much attention from economists and physicists.

SDGNN: Learning Node Representation for Signed Directed Networks

1 code implementation7 Jan 2021 JunJie Huang, HuaWei Shen, Liang Hou, Xueqi Cheng

Guided by related sociological theories, we propose a novel Signed Directed Graph Neural Networks model named SDGNN to learn node embeddings for signed directed networks.

Network Embedding

Beyond Low-frequency Information in Graph Convolutional Networks

1 code implementation4 Jan 2021 Deyu Bo, Xiao Wang, Chuan Shi, HuaWei Shen

For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types of networks.

Node Classification on Non-Homophilic (Heterophilic) Graphs

Towards Powerful Graph Neural Networks: Diversity Matters

no code implementations1 Jan 2021 Xu Bingbing, HuaWei Shen, Qi Cao, YuanHao Liu, Keting Cen, Xueqi Cheng

For a target node, diverse sampling offers it diverse neighborhoods, i. e., rooted sub-graphs, and the representation of target node is finally obtained via aggregating the representation of diverse neighborhoods obtained using any GNN model.

Graph Representation Learning Node Classification

Learning content and context with language bias for Visual Question Answering

1 code implementation21 Dec 2020 Chao Yang, Su Feng, Dongsheng Li, HuaWei Shen, Guoqing Wang, Bin Jiang

Many works concentrate on how to reduce language bias which makes models answer questions ignoring visual content and language context.

Question Answering Visual Question Answering

Slimmable Generative Adversarial Networks

1 code implementation10 Dec 2020 Liang Hou, Zehuan Yuan, Lei Huang, HuaWei Shen, Xueqi Cheng, Changhu Wang

In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power.

AugSplicing: Synchronized Behavior Detection in Streaming Tensors

1 code implementation3 Dec 2020 Jiabao Zhang, Shenghua Liu, Wenting Hou, Siddharth Bhatia, HuaWei Shen, Wenjian Yu, Xueqi Cheng

Therefore, we propose a fast streaming algorithm, AugSplicing, which can detect the top dense blocks by incrementally splicing the previous detection with the incoming ones in new tuples, avoiding re-runs over all the history data at every tracking time step.


Summarizing graphs using configuration model

no code implementations19 Oct 2020 Houquan Zhou, Shenghua Liu, Kyuhan Lee, Kijung Shin, HuaWei Shen, Xueqi Cheng

As a solution, graph summarization, which aims to find a compact representation that preserves the important properties of a given graph, has received much attention, and numerous algorithms have been developed for it.

Social and Information Networks

DeepHawkes: Bridging the gap between prediction and understanding of information cascades

1 code implementation CIKM 2017 Qi Cao, HuaWei Shen, Keting Cen, Wentao Ouyang, Xueqi Cheng

In this paper, we propose DeepHawkes to combat the defects of existing methods, leveraging end-to-end deep learning to make an analogy to interpretable factors of Hawkes process — a widely-used generative process to model information cascade.

Cascade Dynamics Modeling with Attention-based Recurrent Neural Network

1 code implementation1 May 2017 Yongqing Wang, HuaWei Shen, Shenghua Liu, Jinhua Gao, and Xueqi Cheng

However, for cascade prediction, each cascade generally corresponds to a diffusion tree, causing cross-dependence in cascade— one sharing behavior could be triggered by its non-immediate predecessor in the memory chain.


Cannot find the paper you are looking for? You can Submit a new open access paper.